Triple
T17357579
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | savings and loan crisis of the 1980s |
E421978
|
entity |
| Predicate | numberOfFailedInstitutions |
P33611
|
FINISHED |
| Object | over 1000 savings and loan associations |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: over 1000 savings and loan associations | Statement: [savings and loan crisis of the 1980s, numberOfFailedInstitutions, over 1000 savings and loan associations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfFailedInstitutions Context triple: [savings and loan crisis of the 1980s, numberOfFailedInstitutions, over 1000 savings and loan associations]
-
A.
numberOfTargetInstitutions
Indicates the count of institutions that are designated or identified as targets in a given context or dataset.
-
B.
numberOfFailures
chosen
Indicates the count of times an action, process, or condition has failed.
-
C.
hasNumberOfMemberInstitutions
Indicates the quantitative count of member institutions associated with a given entity.
-
D.
partialFailures
Indicates that the relationship or action was only partially successful, with some attempts or components failing while others succeeded.
-
E.
failureRate
Indicates the proportion or frequency at which a system, component, or process fails over a specified set of operations or time period.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d889d520008190a26917a95bf1c2ea |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a4976788190b00c00f710be6c46 |
completed | April 19, 2026, 2:13 a.m. |
| PD | Predicate disambiguation | batch_69e3b02662d08190a07d0fb5c04b6f33 |
completed | April 18, 2026, 4:24 p.m. |
Created at: April 10, 2026, 5:44 a.m.